Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    listing approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    über
    0.39
     ስርዓ
    0.38
    inities
    0.38
    itness
    0.38
    eline
    0.37
    ınd
    0.36
     statt
    0.35
    အတွင်း
    0.35
    jen
    0.35
    之类的
    0.35
    POSITIVE LOGITS
    一是
    0.91
     firstly
    0.73
     Either
    0.69
     Firstly
    0.69
    两种
    0.68
    兩種
    0.67
    一个是
    0.64
     either
    0.62
    有两种
    0.61
     dwóch
    0.60
    Act Density 0.366%

    No Known Activations